Reckoning Machines

Simple yet Powerful

Technology for research and forecasting.

Better reckoning, with machines.

As AI makes models and code cheaper, the scarce resource becomes the context, judgment and institutional knowledge that make them useful.

We build systems that preserve what a team knows and bring that knowledge into its next decision. We integrate them into the daily work of investment and corporate finance teams.

Explore our products

Built by Reckoning Machines

Our products

IRIS preserves the reasoning behind an Excel forecast. Context Compiler assembles the evidence a task requires. The Adaptive Research Harness keeps a record of the experiments behind a research finding.

cc — Context Compiler

Objective: more reasoning per token. Not yet measured.

Context Compiler turns prepared evidence, such as typed records and declared tables, into structured input for an AI model. Each selected figure links to its source. When selected estimates conflict, the compiler shows the competing values.

Explore cc
A highlighted filing cell passes through four compiler layers. A brass line connects the cell, its dependencies and a row in the compiled context.
Source evidence
Quarterly filing, earnings release, broker estimates, transcript
Compiler
Meaning, authority, dependencies, Attention
Context
Required and supporting evidence, coverage, source handles

In the investment example, a reported deposit cost travels with the interest expense and average deposit balances it is computed from. Each selected figure links to its source.

ExcelClaude alongside

IRIS

Ask the whole book.

IRIS turns a collection of financial models into a research system. Ask questions across your entire book, understand what drives the numbers, and trace conclusions to their sources.

Claude owns the horizontal intelligence. IRIS owns the vertical context.

IRIS gives Claude context for each model and keeps the research and reasoning the team chooses to retain. As that investment history grows, every analyst becomes more effective.

  • Analysts build and update Excel forecasts with Claude alongside them.
  • PMs see the whole book and ask how a question plays out across company models.
  • Follow the assumptions and calculations behind a forecast.
  • See what the numbers mean for the underlying business.
  • A Method is a forecasting skill with its evidence attached, and IRIS remembers every time you change it.
  • Return to the analyst's reasoning as the company and thesis change.
  • Review and approve proposed changes, with a record the team can inspect and rerun.

Semantic compression ties it together by giving Claude a compact account of the model, so it spends tokens on the question rather than on rediscovering the spreadsheet every time.

Analysts start from the IRIS Model Catalog rather than a blank sheet.

Supervised pilot with two investment firms. Access is arranged with us.

irisos.dev
DialogPaper book

Adaptive Research Harness | DIALOG

The Adaptive Research Harness holds research agents to account for what they try, and Dialog is the trading desk that runs on it.

  • Research agents now produce more ideas than a team can check, and the best-looking result of many attempts is not the same as one that will hold up.
  • ARH writes each attempt to the record before the next can start, with its question, its reserved budget, its result and its failures, so the count of attempts is a fact of the record rather than a recollection.
  • A separate evaluator checks each proposed conclusion, and a result enters the accepted record only under rules the owner has set.
  • Rejected work stays in the record, so the next researcher sees the failed variants and the decisions behind what was accepted.
  • Researchers and evaluators can be replaced while the acceptance rules stay in place, so a team can change its agents without losing what it has learned.
  • Dialog puts the harness to work on a paper desk. Competing research approaches develop hypotheses, an independent evaluator checks them, and the strategies that pass share one portfolio with orders, fills, cash and fees accounted for.

Budget makes the search visible and separate acceptance makes the result accountable, so when a strategy is challenged the history shows how much searching it took to find it and why it was accepted.

Open prototypes on GitHub. Synthetic data and paper execution.

View ARH on GitHub View DIALOG on GitHub

Advisory

We solve forecasting problems.

We build the system and run it alongside the team until it is handed over.

Investment firms

We have twice built a systematic equity platform and taken it through to live trading. The most recent one carries portfolio construction, optimization, order management and execution, with an LLM runner making about 11,000 calls per cycle inside the data pipeline. For a fundamental research team the same engineering puts AI models inside the research process with IRIS.

Corporate finance and FP&A

For a global payments company we built the profitability and unit-economics model for a new product and paired it with Monte Carlo scenario analysis. A large pharmaceutical company needed a way to decide which AI-enabled commercial investments to fund and which to test first. We built that decision framework on Monte Carlo and value-of-information analysis.

Point of view

As code gets cheaper, context and control matter more.

AI makes it easier to build and run forecasts, tests, and research agents. At scale, teams need to know which assumptions and evidence produced each result, what changed, and why a conclusion was accepted.

AI that proposes, a record of what it proposed, and a person who decides.

About

Run by an investor who builds the systems.

Jed Gore

Jed Gore, CFA, started as a software engineer on prime brokerage systems. He then spent nineteen years investing in financial-services stocks, five of them as portfolio manager of a $250 million portfolio at Diamondback Capital. Since 2017 he has built research and analytics platforms for investors. He has been the sole engineer on two systematic equity platforms taken to live trading, and ran the portfolio on one of them. He is a named inventor on a U.S. patent for extracting tables from financial filings.

Contact

One email starts it.

Talk to us about integrating cc into your evidence workflow, bringing IRIS to your research team, or building a forecasting system.

Email Reckoning Machines